Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions related to political parties

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alam
    -0.87
     Kard
    -0.75
     Reloaded
    -0.75
     Maw
    -0.72
     Hoo
    -0.69
     Bulg
    -0.69
    arcity
    -0.67
     Tile
    -0.67
     Grizz
    -0.65
    angelo
    -0.65
    POSITIVE LOGITS
     affiliation
    1.11
     affili
    0.99
    leader
    0.89
     insiders
    0.88
     primaries
    0.87
    goers
    0.86
     caucuses
    0.85
     leaders
    0.85
     congress
    0.82
    Leader
    0.81
    Act Density 0.030%

    No Known Activations